Recognition of general patterns using neural networks
New learning rules for Hopfield-like networks are suggested. They permit non-orthogonal patterns to be associatively recalled similarly as orthogonal or pseudoorthogonal ones are treated by the well-known models. The formula for synaptic weight \(T_{ij}=\sum \mu^ s_ i\mu^ s_ j\), where the sum is taken over all taught patterns from their set \(\{\mu^ s\}\), is generalized to \(T_{ij}=\sum \epsilon_ s\mu^ s_ i\xi^ s_ j\), where \(\epsilon_ s\) denotes a relative teaching strength of the s-th pattern and \(\xi^ s_ j\) is a component of the vector \(\xi^ s\), which is constructed as a linear combination of vectors \(\{\mu^ s\}\) in such a way that a modified orthogonality condition is satisfied. The matrix \(\| T_{ij}\|\) is generally not symmetric, yet stability of taught patterns is proved. Global stability has only empirically been tested. A time-dependent energy function is proposed as a tool for further investigation of behaviour of networks with asymmetric memory matrix.
- ``Neural computation of decisions in optimization problems
- A model of distributed type associative memory with quantized Hadamard transform
- scientific article; zbMATH DE number 3965458 (Why is no real title available?)
- Neural networks and physical systems with emergent collective computational abilities
- Neurons with graded response have collective computational properties like those of two-state neurons
- Associative recognition and storage in a model network of physiological neurons
- Stability and attractivity in associative memory networks
- Group actions and learning for a family of automata
- Neural networks as systems for recognizing patterns
- High-symmetry Hopfield-type neural networks
- Modeling distributed concept representation in Hopfield neural networks.
- A network of multitate units capable of associative memory and pattern classification
- A model of orthogonal auto-associative networks
- On a perceptron-type learning rule for higher order Hopfield neural networks including dilation and translation
- Dynamic properties and a new learning mechanism in higher order neural networks
- Order parameters in a Hopfield neural network
- Configuring interaction of memorized patterns with an asymmetric Hebbian rule for recurrent neural networks
- Pattern-specific neural network design
- A Widrow-Hoff learning rule for a generalization of the linear auto-associator
- Application of Hopfield-like neural networks to nonlinear factorization
- scientific article; zbMATH DE number 4206031 (Why is no real title available?)
- On the Hopfield algorithm. Foundations and examples
- Recognition of topological features of graphs and images in neural networks
- Neural Networks, Acyclic Orientations of the Hypercube, and Sets of Orthogonal Vectors
- scientific article; zbMATH DE number 4098738 (Why is no real title available?)
- Neural networks with prescribed large time behaviour
- Derivation of Hebb's rule
- scientific article; zbMATH DE number 1192966 (Why is no real title available?)
- Competition between Hopfield and symmetry transform interactions in a neural net
- scientific article; zbMATH DE number 597653 (Why is no real title available?)
- scientific article; zbMATH DE number 939873 (Why is no real title available?)
- Pattern recognition minimizes entropy production in a neural network of electrical oscillators
- Using generalized principal component analysis to achieve associative memory in a Hopfield net
- Autoassociative Hamming Neural Network
- scientific article; zbMATH DE number 2201931 (Why is no real title available?)
- How to compress sequential memory patterns into periodic oscillations: general reduction rules
- Pattern-recognition by an artificial network derived from biologic neuronal systems
- A spectral approach to Hebbian-like neural networks
This page was built for publication: Recognition of general patterns using neural networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1107333)
